mirror of
https://github.com/sqlmapproject/sqlmap.git
synced 2026-11-21 23:51:09 +00:00
fix(search): parse current Bing result links (#6150)
While looking into #6009 I noticed the Bing fallback in -g never returns anything, even when Bing itself serves a normal results page. Two things changed on Bing's side. The result anchor now carries target="_blank" before href, so '<h2><a href="..." h=' no longer matches at all. And the href is no longer the target URL but a tracking redirect (https://www.bing.com/ck/a?...&u=a1<base64url>), where the real link sits base64url-encoded after the "a1" prefix in the u parameter. The regex now allows extra attributes on both tags and captures either the u payload of a ck/a redirect or a plain href. The payload is decoded with decodeBase64(), which already deals with the URL-safe alphabet and the missing padding. Plain hrefs still work the same as before (with & unescaped), in case Bing serves the old markup to some clients. Checked against a saved live results page (0 -> 10 links) and the old markup, and --smoke-test passes. Google still can't be scraped since it only serves a JS page now, so this doesn't fully close #6009, but Bing is usable again as a fallback when DuckDuckGo blocks the IP.
This commit is contained in:
parent
8461fd402b
commit
5e2a6aeec8
2 changed files with 3 additions and 2 deletions
|
|
@ -214,7 +214,7 @@ GOOGLE_CONSENT_COOKIE = "CONSENT=YES+shp.gws-%s-0-RC1.%s+FX+740" % (time.strftim
|
|||
DUCKDUCKGO_REGEX = r'<a class="result__url" href="(htt[^"]+)'
|
||||
|
||||
# Regular expression used for extracting results from Bing search
|
||||
BING_REGEX = r'<h2><a href="([^"]+)" h='
|
||||
BING_REGEX = r'<h2[^>]*><a [^>]*href="(?:https?://www\.bing\.com/ck/a\?[^"]*?[?;]u=a1([^&"]+)[^"]*|([^"]+))"'
|
||||
|
||||
# Dummy user agent for search (if default one returns different results)
|
||||
DUMMY_SEARCH_USER_AGENT = "Mozilla/5.0 (X11; Linux x86_64; rv:141.0) Gecko/20100101 Firefox/141.0"
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue